Privacy-Preserving Sports Wearable Data Fusion Framework

Area of Science:

• Sports Science and Technology
• Data Privacy and Security
• Biomedical Engineering

Background:

• The sports industry increasingly relies on real-time data from wearable sensors for athlete training and injury prevention.
• The widespread use of diverse wearable technologies raises significant concerns regarding the security of sensitive athlete personal data.
• Potential cyberattacks and data leaks pose a substantial risk to athletes and the sports sector.

Purpose of the Study:

• To present a novel privacy-preserving sports wearable data fusion framework.
• To address the critical need for securing personal data collected by sports wearables.
• To enhance athlete training and physical fitness while safeguarding data confidentiality.

Main Methods:

• Implementation of Lagrange's relaxation method for multi-sensor data assignment and synthesis.
• Integration of differential privacy techniques for secure access to personal data.
• Development of a data fusion framework to consolidate information from various wearable sensors.

Main Results:

• The proposed framework effectively fuses data from multiple sensors while preserving user privacy.
• Demonstrated protection against unauthorized disclosure of athlete identities and personal information.
• Enabled secure utilization of somatometric data for advanced sports analytics.

Conclusions:

• The developed framework offers a robust solution for securing athlete data in the era of smart training.
• It balances the benefits of real-time data analytics with the imperative of personal data protection.
• This approach is crucial for the ethical and secure advancement of sports technology.